Exciting day at #INLG2025 in Hanoi! ๐ป๐ณ
Daniel Russo (@daniel-russo.bsky.social ) and Stefano Menini presented "Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking"
๐ tinyurl.com/3w8jykhd
02.11.2025 04:12 โ ๐ 4 ๐ 2 ๐ฌ 0 ๐ 0
๐ข Do you want to join our group? We opened **two** calls for a fully funded PhD. Details are in the image and at the following links.
Calls: iecs.unitn.it/education/ad...
PhD Details: iecs.unitn.it/education/ad...
Deadline: August 22nd, 2025, hrs. 04:00 PM (CEST)
04.08.2025 08:56 โ ๐ 4 ๐ 5 ๐ฌ 0 ๐ 1
The first invited speaker is Cathy Buerger from @dangerousspeech.orgโฌ, with a talk titled "Co-designing Counterspeech: Rethinking AIโs Role". #ACL2025NLP
27.07.2025 14:39 โ ๐ 7 ๐ 3 ๐ฌ 0 ๐ 0
What ethical questions arise when designing counterspeech? Gavin Abercrombie (@gavina.bsky.social) will guide us with a talk titled "Ethical considerations of counterspeech".
27.07.2025 14:13 โ ๐ 6 ๐ 2 ๐ฌ 0 ๐ 0
What challenges unite counterspeech generation for hate speech and misinformation? Marco Guerini (@marcoguerini.bsky.social) will unpack this intersection.
27.07.2025 13:29 โ ๐ 4 ๐ 2 ๐ฌ 0 ๐ 0
CSHAM continues with Daniel Russo (@daniel-russo.bsky.social) presenting on โNLP approaches to counterspeech for misinformationโ
27.07.2025 13:23 โ ๐ 4 ๐ 2 ๐ฌ 0 ๐ 0
CSHAM continues with Helena Bonaldi (@helenabon.bsky.social) sharing insights on "NLP approaches to counterspeech against hate".
27.07.2025 12:44 โ ๐ 4 ๐ 3 ๐ฌ 0 ๐ 0
The tutorial starts with a presentation from Yi-Ling Chung on "Counterspeech in the real world: evidence from social science".
27.07.2025 12:29 โ ๐ 5 ๐ 1 ๐ฌ 0 ๐ 0
CSHAM started ๐ฅ
Join us in Hall N.1-N.2 at #ACL2025NLP
@marcoguerini.bsky.social
27.07.2025 12:24 โ ๐ 4 ๐ 2 ๐ฌ 0 ๐ 0
Last but not least, we present the CSHAM organisers. Daniel Russo (@daniel-russo.bsky.social), Helena Bonaldi (@helenabon.bsky.social), Yi-Ling Chung, Gavin Abercrombie (@gavina.bsky.social), Marco Guerini (@marcoguerini.bsky.social).
We are excited to see you all tomorrow at 2 pm at #ACL2025NLP ๐
26.07.2025 10:05 โ ๐ 5 ๐ 3 ๐ฌ 0 ๐ 1
LanD(ing) in Vienna for #ACL2025NLP ๐
@daniel-russo.bsky.social @helenabon.bsky.social
@docchipinti8.bsky.social
@marcoguerini.bsky.social
26.07.2025 08:33 โ ๐ 5 ๐ 3 ๐ฌ 0 ๐ 1
LanD(ing) in Vienna for #ACL2025NLP ๐
@daniel-russo.bsky.social @helenabon.bsky.social
@docchipinti8.bsky.social
@marcoguerini.bsky.social
26.07.2025 08:33 โ ๐ 5 ๐ 3 ๐ฌ 0 ๐ 1
CSHAM
Sunday, July 27 - 14:00-17:30
๐ฃ Planning to attend #ACL2025NLP? Then donโt miss the "NLP for Counterspeech against Hate and Misinformation" tutorial!
๐๏ธ Sunday, July 27, 2025
๐ 14:00 - 17:30
๐ ACL2025, Austria Center Vienna
Details on our website โคต๏ธ sites.google.com/view/nlp4csh...
08.07.2025 15:03 โ ๐ 3 ๐ 2 ๐ฌ 0 ๐ 0
CSHAM - Program
Sunday, July 27 โ(UTC+1)
Delighted to introduce Cathy Buerger, our first invited speaker for the "NLP for Counterspeech against Hate and Misinformation" tutorial. Join us to hear her insightful work on "Co-designing Counterspeech: Rethinking AI's Role" #ACL2025NLP
More details โคต๏ธ
sites.google.com/view/nlp4csh...
18.07.2025 12:52 โ ๐ 5 ๐ 5 ๐ฌ 0 ๐ 0
All together once again to greet @estrellavr15.bsky.social who is going back to Spain ๐๐ผ
23.07.2025 17:58 โ ๐ 1 ๐ 1 ๐ฌ 0 ๐ 0
CSHAM - Program
Sunday, July 27 โ(UTC+1)
Simone Fontana (@simofons.bsky.social), Editorial Director at @facta.news, is our second invited speaker! His talk, "Countering Disinformation and Hate Speech: The Role of Journalism", will offer insights from a practitionerโs perspective! #ACL2025NLP
Details โคต๏ธ
sites.google.com/view/nlp4csh...
23.07.2025 13:36 โ ๐ 7 ๐ 6 ๐ฌ 0 ๐ 0
7/๐งต ๐ฏFine-tuned models avoid this copy-paste behavior and reflect deeper persona traits, leading to more authentic persona-based dialogue.
04.06.2025 14:17 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
6/๐งต๐ฏ Zero-shot models (seem to) perform much better than fine-tuned ones, but only because they copy biographical details from the prompt, making speaker identification trivial and conversations shallow.
04.06.2025 14:17 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
5/๐งต ๐ฏ LLMs are able to generalize to โunfamiliarโ topics (Harry speaking about kryptonite).
04.06.2025 14:17 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
4/๐งต ๐ฏ LLMs are not able to generalize to โunfamiliarโ interlocutors (Harry speaking with Superman).
04.06.2025 14:17 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
3/๐งต ๐ฏ Speaker personas are easier to recognize when we know the interlocutorโs bio. Thus LLMs donโt just follow their own persona, but adapt to their conversation partner. Stillโฆ
04.06.2025 14:17 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
2/๐งต We cast the problem as a speaker recognition task: given a dialogue, guess the biography of the target speaker. Is it easier to guess if we also know the interlocutorโs biography? Is it easier if both know each other?
๐ง Following our key findings:
04.06.2025 14:17 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
What happens when Harry meets Superman instead of Sally for a chat? ๐ง๐ฆธโโ๏ธ
We explore how LLMs adapt their responses not just to their given persona, but also to their interlocutorsโ.
๐ฃ New #ACL2025NLP (main) paper by @docchipinti8.bsky.social @marcoguerini.bsky.social @malvinanissim.bsky.social
1/๐งต
04.06.2025 14:17 โ ๐ 3 ๐ 2 ๐ฌ 1 ๐ 2
Tutorials
ACL 2025 Conference Overview.
๐ฃ๏ธ Discover "NLP for Counterspeech against Hate and Misinformation" at #ACL2025NLP! This tutorial bridges CS, social sciences & policy, exploring among others the role of LLMs. #HateSpeech #Misinformation #NLProc #ResponsibleAI
๐ 2025.aclweb.org/program/tuto...
03.06.2025 08:59 โ ๐ 13 ๐ 6 ๐ฌ 0 ๐ 2
CSHAM
Sunday, July 27 - 14:00-17:30
We are happy to announce our tutorial, "NLP for Counterspeech against Hate and Misinformation".
It will be held on July 27, 2025, at #ACL2025NLP in Vienna, Austria!
Stay tuned for more details ๐
sites.google.com/view/nlp4csh...
30.05.2025 12:23 โ ๐ 7 ๐ 2 ๐ฌ 0 ๐ 2
๐ We are excited to share that 3 of our papers made it into #ACL2025NLP!
Massive congrats to the authors:
@docchipinti8.bsky.social, @daniel-russo.bsky.social, Stefano Menini, Fariba Sadeghi, @ziorufus.bsky.social, @marcoguerini.bsky.social, @malvinanissim.bsky.social.
More details coming soon! ๐
03.06.2025 14:37 โ ๐ 4 ๐ 0 ๐ฌ 0 ๐ 3
"NLP for Counterspeech against Hate and Misinformation" tutorial, to be held at joint ACL 2025 conference on July 27.
Working on #NLProc for social good.
Currently at LTI at CMU. ๐ณโ๐
The Milan Natural Language Processing Group #NLProc #AI
milanlproc.github.io
Head of LanD research group at FBK - Italy | NLP for Social Good.
Account dell'Associazione Italiana di Linguistica Computazionale / Account of the Italian Association of Computational Linguistics, http://www.ai-lc.it/
#MachineTranslation Research Unit @ Fondazione Bruno Kessler
#nlproc #deeplearning #ai
mt.fbk.eu
Assistant Professor at Bocconi University in MilaNLP group โข Working in #NLP, #HateSpeech and #Ethics โข She/her โข #ERCStG PERSONAE
Assistant Professor at LIACS, Leiden University
Working in NLP for Social Good โข Human-centered NLP โข Emotions โข HateSpeech โข Fairness โข Ethics โข ๐Awards: SCIE, BBVA Foundation, SEPLN โข โ๏ธ๐ฅพ๐๐
๐ The Netherlands ๐ท๐ง๐ฒ
๐ ๐ช๐ธโ๏ธ๐๐ป
๐ฉ๐ปโ๐ป https://fmplaza.github.io/
PhDing @unimib ๐ฎ๐น & @gronlp.bsky.social ๐ณ๐ฑ, interpretability et similia
danielsc4.it
Computer Science PhD student at Bielefeld University -
NLProc and Computational Social Science -
Disagreement, Human Label Variation, Perspectives -
Website: https://orlikow.ski
Interdisciplinary physicist
Head of the CHuB research unit at FBK
Human behaviour, mobility, transport, decision making, infodemics, data science
Professor @milanlp.bsky.social for #NLProc, compsocsci, #ML
Also at http://dirkhovy.com/
PhD student at the University of Trento and @fbk-mt.bsky.social, working on gender-inclusive machine translation (he/him)
Applied Scientist Intern at Amazon
apierg.github.io
#NLP #NLProc #MT
Computational linguistics and #nlp researcher @dh-fbk.bsky.social
https://ca-milla.github.io
๐ป PhD Student at @dh-fbk.bsky.social @mobs-fbk.bsky.social @land-fbk.bsky.social
๐ฎ๐น FBK, University of Trento
๐ช๐บ @ellis.eu
โ NLP, CSS and coffee
https://nicolopenzo.github.io/
Digital Humanities Research Group at Fondazione Bruno Kessler, Italy
๐ dh.fbk.eu
๐ซ PhD student at @land-fbk.bsky.social
๐ University of Trento
๐ข FBK โ Fondazione Bruno Kessler
๐ค ML, NLP & Crisis Management
natural language things @ https://sites.google.com/site/hwinteractionlab/
gavinabercrombie.github.io
Euskaldun berria
Tha beagan Gร idhlig agam
PhD Student at @gronlp.bsky.social ๐ฎ, core dev @inseq.org. Interpretability โฉ HCI โฉ #NLProc.
gsarti.com